More Like this

1. The lottery ticket hypothesis for pre-trained BERT networks

   Chen, Tianlong ; Frankle, Jonathan ; Chang, Shiyu ; Liu, Sijia ; Zhang, Yang ; Wang, Zhangyang ; Carbin, Michael ( December 2020 , Advances in neural information processing systems)

   null (Ed.)

   In natural language processing (NLP), enormous pre-trained models like BERT have become the standard starting point for training on a range of downstream tasks, and similar trends are emerging in other areas of deep learning. In parallel, work on the lottery ticket hypothesis has shown that models for NLP and computer vision contain smaller matching subnetworks capable of training in isolation to full accuracy and transferring to other tasks. In this work, we combine these observations to assess whether such trainable, transferrable subnetworks exist in pre-trained BERT models. For a range of downstream tasks, we indeed find matching subnetworks at 40% to 90% sparsity. We find these subnetworks at (pre-trained) initialization, a deviation from prior NLP research where they emerge only after some amount of training. Subnetworks found on the masked language modeling task (the same task used to pre-train the model) transfer universally; those found on other tasks transfer in a limited fashion if at all. As large-scale pre-training becomes an increasingly central paradigm in deep learning, our results demonstrate that the main lottery ticket observations remain relevant in this context. 

   more » « less
2. Learning Low-Precision Structured Subnetworks Using Joint Layerwise Channel Pruning and Uniform Quantization

   https://doi.org/10.3390/app12157829  

   Zhang, Xinyu ; Colbert, Ian ; Das, Srinjoy ( August 2022 , Applied Sciences)

   Pruning and quantization are core techniques used to reduce the inference costs of deep neural networks. Among the state-of-the-art pruning techniques, magnitude-based pruning algorithms have demonstrated consistent success in the reduction of both weight and feature map complexity. However, we find that existing measures of neuron (or channel) importance estimation used for such pruning procedures have at least one of two limitations: (1) failure to consider the interdependence between successive layers; and/or (2) performing the estimation in a parametric setting or by using distributional assumptions on the feature maps. In this work, we demonstrate that the importance rankings of the output neurons of a given layer strongly depend on the sparsity level of the preceding layer, and therefore, naïvely estimating neuron importance to drive magnitude-based pruning will lead to suboptimal performance. Informed by this observation, we propose a purely data-driven nonparametric, magnitude-based channel pruning strategy that works in a greedy manner based on the activations of the previous sparsified layer. We demonstrate that our proposed method works effectively in combination with statistics-based quantization techniques to generate low precision structured subnetworks that can be efficiently accelerated by hardware platforms such as GPUs and FPGAs. Using our proposed algorithms, we demonstrate increased performance per memory footprint over existing solutions across a range of discriminative and generative networks. 

   more » « less
3. Optimal Eye Surgeon: Finding image priors through sparse generators at initialization

   Ghosh, Avrajit ; Zhang, Xitong ; Sun, Kenneth K ; Qu, Qing ; Ravishankar, Saiprasad ; Wang, Rongrong ( June 2024 , International Conference on Machine Learning)

   We introduce Optimal Eye Surgeon (OES), a framework for pruning and training deep image generator networks. Typically, untrained deep convolutional networks, which include image sampling operations, serve as effective image priors (Ulyanov et al., 2018). However, they tend to overfit to noise in image restoration tasks due to being overparameterized. OES addresses this by adaptively pruning networks at random initialization to a level of underparameterization. This process effectively captures low-frequency image components even without training, by just masking. When trained to fit noisy images, these pruned subnetworks, which we term Sparse-DIP, resist overfitting to noise. This benefit arises from underparameterization and the regularization effect of masking, constraining them in the manifold of image priors. We demonstrate that subnetworks pruned through OES surpass other leading pruning methods, such as the Lottery Ticket Hypothesis, which is known to be suboptimal for image recovery tasks (Wu et al., 2023). Our extensive experiments demonstrate the transferability of OES-masks and the characteristics of sparse-subnetworks for image generation. 

   more » « less
4. Harmonious Coexistence of Structured Weight Pruning and Ternarization for Deep Neural Networks

   https://doi.org/10.1609/aaai.v34i04.6138  

   Yang, Li ; He, Zhezhi ; Fan, Deliang ( June 2020 , Proceedings of the AAAI Conference on Artificial Intelligence)

   Deep convolutional neural network (DNN) has demonstrated phenomenal success and been widely used in many computer vision tasks. However, its enormous model size and high computing complexity prohibits its wide deployment into resource limited embedded system, such as FPGA and mGPU. As the two most widely adopted model compression techniques, weight pruning and quantization compress DNN model through introducing weight sparsity (i.e., forcing partial weights as zeros) and quantizing weights into limited bit-width values, respectively. Although there are works attempting to combine the weight pruning and quantization, we still observe disharmony between weight pruning and quantization, especially when more aggressive compression schemes (e.g., Structured pruning and low bit-width quantization) are used. In this work, taking FPGA as the test computing platform and Processing Elements (PE) as the basic parallel computing unit, we first propose a PE-wise structured pruning scheme, which introduces weight sparsification with considering of the architecture of PE. In addition, we integrate it with an optimized weight ternarization approach which quantizes weights into ternary values ({-1,0,+1}), thus converting the dominant convolution operations in DNN from multiplication-and-accumulation (MAC) to addition-only, as well as compressing the original model (from 32-bit floating point to 2-bit ternary representation) by at least 16 times. Then, we investigate and solve the coexistence issue between PE-wise Structured pruning and ternarization, through proposing a Weight Penalty Clipping (WPC) technique with self-adapting threshold. Our experiment shows that the fusion of our proposed techniques can achieve the best state-of-the-art ∼21× PE-wise structured compression rate with merely 1.74%/0.94% (top-1/top-5) accuracy degradation of ResNet-18 on ImageNet dataset. 

   more » « less
5. Pruning neural networks without any data by iteratively conserving synaptic flow

   Tanaka, H. ; Kunin, D. ; Yamins, Y. ; Ganguli, S ( December 2020 , Advances in neural information processing systems)

   null (Ed.)

   Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training and pruning cycles, the existence of winning lottery tickets or sparse trainable subnetworks at initialization. This raises a foundational question: can we identify highly sparse trainable subnetworks at initialization, without ever training, or indeed without ever looking at the data? We provide an affirmative answer to this question through theory driven algorithm design. We first mathematically formulate and experimentally verify a conservation law that explains why existing gradient-based pruning algorithms at initialization suffer from layer-collapse, the premature pruning of an entire layer rendering a network untrainable. This theory also elucidates how layer-collapse can be entirely avoided, motivating a novel pruning algorithm Iterative Synaptic Flow Pruning (SynFlow). This algorithm can be interpreted as preserving the total flow of synaptic strengths through the network at initialization subject to a sparsity constraint. Notably, this algorithm makes no reference to the training data and consistently competes with or outperforms existing state-of-the-art pruning algorithms at initialization over a range of models (VGG and ResNet), datasets (CIFAR-10/100 and Tiny ImageNet), and sparsity constraints (up to 99.99 percent). Thus our data-agnostic pruning algorithm challenges the existing paradigm that, at initialization, data must be used to quantify which synapses are important. 

   more » « less